User | AlexSwitch |
Upload Date | December 09 2024 03:01 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | Mac mini (2023) |
Model ID | Mac14,12 |
Motherboard | Mac14,12 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.48 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1405
261.4 IPS |
|
Image Classification (HP)
|
100% |
14891
2.77 KIPS |
|
Image Classification (Q)
|
96% |
17760
3.32 KIPS |
|
Image Segmentation (SP)
|
100% |
1704
27.6 IPS |
|
Image Segmentation (HP)
|
100% |
19540
316.8 IPS |
|
Image Segmentation (Q)
|
99% |
24803
402.1 IPS |
|
Pose Estimation (SP)
|
100% |
12977
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
107905
125.9 IPS |
|
Pose Estimation (Q)
|
95% |
106294
124.6 IPS |
|
Object Detection (SP)
|
100% |
1690
134.1 IPS |
|
Object Detection (HP)
|
99% |
16167
1.29 KIPS |
|
Object Detection (Q)
|
91% |
17689
1.41 KIPS |
|
Face Detection (SP)
|
100% |
3628
43.1 IPS |
|
Face Detection (HP)
|
100% |
36728
436.4 IPS |
|
Face Detection (Q)
|
100% |
46824
556.4 IPS |
|
Depth Estimation (SP)
|
100% |
6254
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
88430
681.3 IPS |
|
Depth Estimation (Q)
|
85% |
110277
861.8 IPS |
|
Style Transfer (SP)
|
100% |
24978
32.1 IPS |
|
Style Transfer (HP)
|
100% |
206468
265.4 IPS |
|
Style Transfer (Q)
|
96% |
198020
255.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5089
187.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
42755
1.58 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49394
1.82 KIPS |
|
Text Classification (SP)
|
100% |
2340
3.12 KIPS |
|
Text Classification (HP)
|
100% |
4045
5.40 KIPS |
|
Text Classification (Q)
|
93% |
4037
5.42 KIPS |
|
Machine Translation (SP)
|
100% |
4323
74.5 IPS |
|
Machine Translation (HP)
|
100% |
4007
69.0 IPS |
|
Machine Translation (Q)
|
98% |
4255
73.5 IPS |